CN114789743B - Method and system for monitoring abnormal running of train wheels - Google Patents
Method and system for monitoring abnormal running of train wheels Download PDFInfo
- Publication number
- CN114789743B CN114789743B CN202210708800.3A CN202210708800A CN114789743B CN 114789743 B CN114789743 B CN 114789743B CN 202210708800 A CN202210708800 A CN 202210708800A CN 114789743 B CN114789743 B CN 114789743B
- Authority
- CN
- China
- Prior art keywords
- wheel
- abnormal
- signal
- signals
- monitoring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61K—AUXILIARY EQUIPMENT SPECIALLY ADAPTED FOR RAILWAYS, NOT OTHERWISE PROVIDED FOR
- B61K9/00—Railway vehicle profile gauges; Detecting or indicating overheating of components; Apparatus on locomotives or cars to indicate bad track sections; General design of track recording vehicles
- B61K9/12—Measuring or surveying wheel-rims
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Train Traffic Observation, Control, And Security (AREA)
Abstract
The invention discloses a method and a system for monitoring the abnormal operation of train wheels, wherein the method comprises the following steps: dividing the acquired signals and recombining the signals into signals of a single wheel; filtering and denoising the recombined signal; step-shifting and frame-selecting the noise-reduced signals by using a sliding window, and calculating the kurtosis value of each segment of signals selected by frames; setting the signal with the kurtosis value larger than the threshold value as an abnormal region; expanding the width of a sliding window of the abnormal area, calculating a peak value factor of the signal selected by the frame and extracting the abnormal frequency spectrum characteristic of the signal; and judging the wheel state according to the peak factor and the abnormal frequency spectrum characteristic. The invention can avoid rail replacement operation by changing the installation position of the sensor, and is easy to install and convenient to maintain. By changing the layout of the measuring area, the running state of the wheel can be continuously measured, and subsequent signals can be spliced and processed conveniently.
Description
Technical Field
The invention relates to a method and a system for monitoring train wheel operation abnormity.
Background
When a train runs at a high speed, the interaction force between the train and a rail is enhanced, the problems of abrasion and abrasion between wheels and steel rails, contact fatigue and wheel out-of-round are increased gradually, the dynamic response between the train and a rail system structure is changed due to the problems, one of the train and the rail system causes the other one to be abnormal, and the service life and the stability of each part of a railway system are seriously influenced. At present, for the abnormal detection of the running of the wheel, the circumference of the whole wheel is covered by different mounting modes of the rail edge sensor for detection.
At present, the optical fiber sensor is clamped below the steel rail to detect the vibration and the deformation of the steel rail, a longer detection distance is required to be arranged to cover a circumference and a space below the steel rail as much as possible, and the replacement of the sleeper is required to ensure the stability and the accuracy of detection when the train passes through by detecting the strain sensor arranged above the sleeper and at the rail waist, so that the requirement on detection site selection is high, the installation is complex, and more labor is required to be consumed.
Disclosure of Invention
In view of the above, the invention provides a method and a system for monitoring abnormal operation of train wheels, which have low requirements for installation and site selection and do not need to move a steel rail to replace a sleeper.
In order to solve the technical problems, the technical scheme of the invention is as follows: a train wheel operation abnormity monitoring method comprises the following steps:
dividing the acquired signals and recombining the signals into signals of a single wheel;
filtering and denoising the recombined signal;
step-shifting and frame-selecting the noise-reduced signals by using a sliding window, and calculating the kurtosis value of each segment of signals selected by frames; setting the signal with the kurtosis value larger than the threshold as an abnormal region;
expanding the width of a sliding window of the abnormal area, calculating a peak value factor of the signal selected by the frame and extracting the abnormal frequency spectrum characteristic of the signal;
and judging the wheel state according to the peak factor and the abnormal frequency spectrum characteristic.
As an improvement, the signal based on splitting and recombining into individual wheels comprises:
acquiring the start-stop time of each wheel passing through each measuring area, and intercepting the effective waveform section of each wheel passing through each measuring area by using the start-stop time;
and splicing the intercepted effective waveform segments to obtain a signal of each wheel.
As an improvement, a wavelet filtering algorithm is adopted to carry out filtering and noise reduction on the recombined signal.
Preferably, the width of the sliding window is 0.1-1 times of the circumference of the wheel, the step length is 0.05-1 times of the circumference of the wheel, and the step length is less than or equal to the width of the sliding window.
As an improvement, using a formula
Calculating kurtosis value, wherein K is the calculated kurtosis value, N is the sampling length,
is standard deviation, x i For each time-of-day signal value,
is the mean value of the signal.
Preferably, the sliding window is expanded 1/3 in the direction of travel by the window width.
As an improvement, using a formula
Calculating a crest factor, wherein C is the crest factor, x peak Is the peak value, x rms Is the root mean square value.
As an improvement, the Fourier transform is used to obtain the frequency spectrum characteristics of the signal, and abnormal frequency spectrum characteristics are extracted from the frequency spectrum characteristics.
As an improvement, the judging the wheel state based on the peak factor and the abnormal spectral feature includes:
fitting a peak factor-wheel anomaly function through previously known data;
substituting the calculated peak factor and the wheel speed into a peak factor-wheel abnormal degree function to obtain the wheel abnormal degree;
and judging the wheel state by using the wheel abnormal degree and the abnormal frequency spectrum characteristics.
The invention also provides a system for monitoring the abnormal operation of the train wheels, which comprises:
the signal acquisition unit is used for acquiring wheel signals;
the signal segmentation and recombination unit is used for segmenting and recombining the acquired wheel signals into signals of a single wheel;
the filtering and noise reducing unit is used for filtering and noise reducing the recombined signal;
the abnormal region selection unit is used for performing step-shifting frame selection on the noise-reduced signals by using a sliding window and calculating the kurtosis value of each segment of signals selected by the frame; setting the signal with the kurtosis value larger than the threshold value as an abnormal region;
the peak factor abnormal spectrum feature acquisition unit is used for expanding the width of a sliding window of an abnormal area, calculating a peak factor of a signal selected by a frame and extracting the abnormal spectrum feature of the signal;
and the wheel state judging unit is used for judging the wheel state according to the peak factor and the abnormal frequency spectrum characteristic.
As an improvement, the signal acquisition unit comprises a plurality of pressure sensors and a plurality of shear sensors; each pressure sensor corresponds to one sleeper, and three continuous pressure sensors and two shear sensors which are respectively arranged in front of and behind the three pressure sensors form a measuring area; the measuring areas are three or more, and the adjacent measuring areas are partially overlapped.
Preferably, a pressure sensor and a shear sensor are coincident in adjacent measurement areas.
As an improvement, the pressure sensor is arranged on the top surface of the rail bottom of the rail at the sleeper, and the shear force sensor is arranged on the rail web.
The invention has the advantages that:
1. through changing the sensor mounted position, can avoid trading the rail operation, easily simple to operate is convenient for maintain.
2. By changing the layout of the measuring area, the running state of the wheel can be continuously measured, and subsequent signals can be spliced and processed conveniently.
3. And the interference of the electrical noise on the extraction of subsequent abnormal values is reduced by denoising the rear-end signal.
4. When abnormal values are extracted and processed, the kurtosis is calculated by adopting windowing, the interference of a plurality of abnormal parts of the same wheel can be avoided, and then the wheel abnormality is comprehensively judged by obtaining the peak value proportion coefficient and the spectrum characteristic of an abnormal region.
Drawings
Fig. 1 is a layout diagram of a survey area in the prior art.
Fig. 2 is a waveform diagram of a signal acquired in the prior art.
FIG. 3 is a layout diagram of the measurement zones of the present invention.
Fig. 4 is a waveform diagram of a signal acquired in the present invention.
Fig. 5 is a schematic view of the installation position of the sensor of the present invention.
Fig. 6 is a schematic diagram of the structure of the present invention.
FIG. 7 is a flow chart of the present invention.
The labels in the figure are: 1 steel rail, 2 sleepers, 3 pressure sensors, 4 shear sensors, 101 rail heads, 102 rail waists and 103 rail bottoms.
Detailed Description
In order that those skilled in the art will better understand the technical solutions of the present invention, the present invention will be further described in detail with reference to the following embodiments.
The running state of the wheel is detected by adopting a force transducer, and the change of the interaction force of the wheel and the rail is detected, so that the downward pressure of the wheel and the shearing force generated by the action of the wheel and the rail need to be detected, and the resultant force of the downward pressure of the wheel and the shearing force is the wheel and rail force. In the prior art, when downward pressure is detected, a pressure sensor pad 3 is usually arranged between the bottom of a steel rail 1 and a sleeper 2, as shown in fig. 1, wheel-rail interaction force when wheels pass through is detected, but in the method, the steel rail needs to be moved and a special sleeper needs to be replaced to ensure the stability of vehicle operation, other interference is avoided being introduced into collected signals, the installation is complex, the operation requirement of rail replacement is high, and the required construction period is long.
For the measurement of the shearing force, the shearing force sensor 4 is required to be arranged at the rail web 102 of the steel rail 1 to be measured, the change of the wheel rail force is measured through the change of the resultant force of the shearing force and the pressure, as shown in fig. 1, the shearing force sensor is a red square as a pressure measuring sensor. In order to cover a full cycle detection, 3 detection zone ranges need to be satisfied, as shown in fig. 1. Due to the characteristics of the shear force detection, when the wheel passes over the shear force sensor 4, a region where the shear force is zero may occur, and therefore there may be incomplete coverage of the wheel circumference according to the layout, and the signal detected according to the layout has a signal break at the intersection of the detection regions as shown in fig. 2. And on subsequent spectrum analysis and abnormal state judgment, misjudgment and missed judgment can be caused, and the detection accuracy is influenced.
In order to solve this problem, as shown in fig. 3 to 6, the present invention provides a train wheel operation abnormality monitoring system, including:
the signal acquisition unit is used for acquiring wheel signals; the signal acquisition unit comprises a plurality of pressure sensors and a plurality of shear sensors; the pressure sensor is arranged on the top surface of the rail bottom of the steel rail at the sleeper, and the shear force sensor is arranged on the rail web of the steel rail. Each pressure sensor corresponds to one sleeper, and three continuous pressure sensors and two shear sensors which are respectively arranged in front of and behind the three pressure sensors form a measuring area; the measuring areas are three or more, and the adjacent measuring areas are partially overlapped. In this embodiment, a pressure sensor and a shear sensor are overlapped in adjacent measurement areas.
The signal segmentation and recombination unit is used for segmenting and recombining the acquired wheel signals into signals of a single wheel;
the filtering and noise reducing unit is used for filtering and noise reducing the recombined signal;
the abnormal region selection unit is used for performing step-shifting frame selection on the noise-reduced signals by using a sliding window and calculating the kurtosis value of each segment of signals selected by the frame; setting the signal with the kurtosis value larger than the threshold as an abnormal region;
the peak factor abnormal spectrum feature acquisition unit is used for expanding the width of a sliding window of an abnormal area, calculating a peak factor of a signal selected by a frame and extracting the abnormal spectrum feature of the signal;
and the wheel state judging unit is used for judging the wheel state according to the peak factor and the abnormal frequency spectrum characteristic.
According to the invention, the steel rail bottom top surface arranged at the sleeper is arranged, the shear force sensor is arranged on the steel rail web, as shown in fig. 5, the difference between the detected wheel pressure at the steel rail bottom top surface and the detected value at the rail bottom surface is not changed greatly, so that the pressure sensor is replaced from the rail bottom surface to the rail bottom top surface, the rail replacement operation can be avoided, and the rail replacement device is easy and convenient to install and maintain. Meanwhile, the layout structure of the measurement area is shown in fig. 3, and 1 measurement area is formed by matching 3 pressure sensors with 2 shear sensors at two ends. The length of 3 measuring areas can reach the complete coverage of the circumference of the wheel, the measuring areas are overlapped with each other, the running state of the wheel can be continuously measured, and the subsequent signal splicing and processing are facilitated. The signal collected is shown in fig. 4, and no fracture exists.
As shown in fig. 7, according to the above detection system, the present invention further provides a method for monitoring abnormal operation of train wheels, which comprises the following steps:
s1, dividing the collected signals and recombining the signals into signals of a single wheel;
s2, filtering and denoising the recombined signal;
s3, performing step-shifting frame selection on the noise-reduced signals by using a sliding window, and calculating the kurtosis value of each segment of signals selected by the frame selection; setting the signal with the kurtosis value larger than the threshold value as an abnormal region;
s4, expanding the width of the sliding window of the abnormal area, calculating the peak factor of the signal selected by the frame and extracting the abnormal frequency spectrum characteristic of the signal;
and S5, judging the wheel state according to the peak value factor and the abnormal frequency spectrum characteristic.
Specifically, in step S1, since the wheel signals collected by the signal collecting unit are of multiple wheels, the signal needs to be divided and recombined to obtain a single wheel signal, which includes:
s11 obtains the start-stop time of each wheel passing through each detection zone, and intercepts the effective waveform segment of each wheel passing through each detection zone using the start-stop time. Calculating the average speed of each wheel in the equipment detection section according to a plurality of axle counting sensors arranged in the equipment detection section, and obtaining the physical position of each wheel at each moment according to the speed, the physical positions of the axle counting sensors and the triggering moment; the physical position of each force cell is taken as a known condition, the time of each wheel passing through each measuring area can be obtained, and an effective waveform section passed by each wheel of each measuring area can be intercepted (because the length of each measuring area is less than the distance between the front wheel and the rear wheel, the waveform superposition interference section of the front wheel and the rear wheel is almost avoided).
And S12 splicing the intercepted effective waveform segments to obtain signals of each wheel. In this embodiment, there are 3 zones, so that the signals of the three zones are spliced together to form a finished wheel signal.
In step S2, the present embodiment applies a wavelet filtering algorithm to perform filtering denoising on the reconstructed signal.
In step S3, in this embodiment, the width of the sliding window is preferably 0.1 to 1 times of the wheel circumference, the step length is preferably 0.05 to 1 times of the wheel circumference, and the step length is less than or equal to the width of the sliding window. And sliding on the wheel signals according to the step length by using the sliding window with the size, and framing a part of signals every sliding step.
Then using the formula
Calculating kurtosis values of the signals of each part selected by the frame, wherein K is the calculated kurtosis value, N is the sampling length,
is standard deviation, x i For each time-of-day signal value,
is the mean value of the signal.
And comparing the calculated kurtosis value with a preset threshold value, and setting a certain segment of signal as an abnormal region if the kurtosis value of the certain segment of signal is greater than the threshold value.
In step S4, the sliding window is preferably expanded 1/3 window widths back and forth in the direction of travel. Since the window sliding stage may divide the useful abnormal waveform into two halves at step S3, the kurtosis value can be used to preliminarily alarm the useful abnormal waveform. However, in order to ensure the integrity of the abnormal information and complete the calculation of the peak factor, the window width needs to be widened. 1/3, the width expansion is not absolute, but other values are possible, but too large affects the accuracy of the calculation for the preliminary location anomaly, and too small may not fully contain the anomaly waveform and its nearby anomaly information.
And then carrying out peak factor calculation on the wheel signal selected by the expanded sliding window frame, specifically, using a formula
Calculating a crest factor, where C is the crest factor, x peak Is the peak value, x rms Is the root mean square value.
And then, carrying out Fourier transform on the wheel signals to obtain the frequency spectrum characteristics of the signals, and extracting abnormal frequency spectrum characteristics from the frequency spectrum characteristics. If the wheel has anomalies such as wheel tread scuffing, peeling, out-of-round such as wheel eccentricity, ellipse, polygon, etc., it will all exhibit different anomalous spectral signatures from a normal wheel.
For example, local impact of wheel rail contact due to abnormality such as abrasion or separation of a wheel tread surface has a strong energy spectrum, is widely distributed in a frequency domain, and is strongest at a natural resonant frequency of a rail. If the wheel is out-of-round abnormal such as wheel eccentricity, ellipse, polygon and the like, the energy on the frequency spectrum is concentrated in a low frequency band, and the concentrated frequency value is related to the periodic acting force change of the out-of-round wheel and the steel rail. Namely, feature extraction is carried out through the amplitude value of the frequency spectrum and the frequency value in the energy concentration.
In step S5, the method first determines the wheel abnormal condition according to the peak factor calculated in the above steps, and then performs comprehensive determination on the wheel state with the extracted abnormal frequency spectrum feature, which specifically includes:
s51 fitting a peak factor-wheel abnormality degree function through the past known data; through basic data of dynamics simulation software and corresponding real vehicle abnormal wheel case data (used for correcting a simulation relation) acquired by equipment, a function of the combined peak value factor and the wheel abnormal degree can be fitted. For example, an n-ary m-th order equation is set. Fitting operation of the dependent variable such as known x1 (peak factor) x2 (vehicle speed) and the known y (abnormal degree) is carried out to obtain a peak factor-wheel abnormal degree function.
S52, substituting the calculated peak factor and the wheel speed into a peak factor-wheel abnormal degree function to obtain the wheel abnormal degree;
s53 determines the wheel state using the wheel abnormality degree and the abnormality spectrum characteristic. The anomaly spectral feature is used to determine the type of anomaly and the peaking factor is used to determine the degree of wheel anomaly. By combining the abnormality type and the abnormality degree, the comprehensive wheel abnormality can be obtained.
The above is only a preferred embodiment of the present invention, and it should be noted that the above preferred embodiment should not be considered as limiting the present invention, and the protection scope of the present invention should be subject to the scope defined by the claims. It will be apparent to those skilled in the art that various modifications and adaptations can be made without departing from the spirit and scope of the invention, and these modifications and adaptations should be considered within the scope of the invention.
Claims (13)
1. A method for monitoring abnormal operation of train wheels is characterized by comprising the following steps:
dividing the acquired signals and recombining the signals into signals of a single wheel;
filtering and denoising the recombined signal;
step-shifting and frame-selecting the noise-reduced signals by using a sliding window, and calculating the kurtosis value of each segment of signals selected by frames; setting the signal with the kurtosis value larger than the threshold as an abnormal region;
expanding the width of a sliding window of the abnormal area, calculating a peak factor of the signal selected by the expanded frame and extracting the abnormal frequency spectrum characteristic of the signal;
and judging the wheel state according to the peak value factor and the abnormal frequency spectrum characteristic.
2. The method of claim 1, wherein the step of segmenting and reconstructing the signals for a single wheel comprises:
acquiring the start-stop time of each wheel passing through each measuring area, and intercepting the effective waveform section of each wheel passing through each measuring area by using the start-stop time;
and splicing the intercepted effective waveform segments to obtain a signal of each wheel.
3. The method for monitoring the abnormal operation of the train wheels according to claim 1, wherein the method comprises the following steps: and filtering and denoising the recombined signal by adopting a wavelet filtering algorithm.
4. The method for monitoring the abnormal operation of the train wheels according to claim 1, wherein the method comprises the following steps: the width of the sliding window is 0.1-1 times of the circumference of the wheel, the step length is 0.05-1 times of the circumference of the wheel, and the step length is not more than the width of the sliding window.
5. The method for monitoring the abnormal operation of the train wheels according to claim 1, wherein the method comprises the following steps: using formulas
Calculating kurtosis value, wherein K is the calculated kurtosis value, N is the sampling length,
is the standard deviation of the measured data to be measured,
for each time-of-day signal value,
is the mean value of the signal.
6. The method for monitoring the abnormal operation of the train wheels according to claim 1, wherein the method comprises the following steps: the sliding window is expanded 1/3 the window width back and forth in the direction of travel.
7. The method for monitoring the abnormal operation of the train wheels according to claim 1, wherein the method comprises the following steps: using formulas
Calculating a crest factor, where C is the crest factor, x peak The peak value, x, of the signal selected for spreading the back box rms The rms value of the signal selected for the extended frame.
8. The method for monitoring the abnormal operation of the train wheels according to claim 1, wherein the method comprises the following steps: and obtaining the frequency spectrum characteristics of the signal by utilizing Fourier transform, and extracting abnormal frequency spectrum characteristics from the frequency spectrum characteristics.
9. The method for monitoring the abnormal operation of the train wheel according to claim 1, wherein the step of judging the state of the train wheel according to the peak factor and the abnormal frequency spectrum characteristic comprises the following steps:
fitting a peak factor-wheel anomaly function through previously known data;
substituting the calculated peak factor and the wheel speed into a peak factor-wheel abnormity degree function to obtain the wheel abnormity degree;
and judging the wheel state by using the wheel abnormal degree and the abnormal frequency spectrum characteristics.
10. A train wheel operation anomaly monitoring system is characterized by comprising:
the signal acquisition unit is used for acquiring wheel signals;
the signal segmentation and recombination unit is used for segmenting and recombining the acquired wheel signals into signals of a single wheel;
the filtering and noise reducing unit is used for filtering and noise reducing the recombined signal;
the abnormal region selection unit is used for performing step-shifting frame selection on the noise-reduced signals by using a sliding window and calculating the kurtosis value of each segment of signals selected by the frame; setting the signal with the kurtosis value larger than the threshold as an abnormal region;
the peak factor abnormal spectrum feature acquisition unit is used for expanding the width of a sliding window of an abnormal area, calculating a peak factor of a signal selected by a frame and extracting the abnormal spectrum feature of the signal;
and the wheel state judging unit is used for judging the wheel state according to the peak value factor and the abnormal frequency spectrum characteristic.
11. The system for monitoring abnormal operation of a train wheel according to claim 10, wherein: the signal acquisition unit comprises a plurality of pressure sensors and a plurality of shear sensors; each pressure sensor corresponds to one sleeper, and three continuous pressure sensors and two shear sensors which are respectively arranged in front of and behind the three pressure sensors form a measuring area; the measuring areas are three or more, and the adjacent measuring areas are partially overlapped.
12. The system for monitoring abnormal operation of train wheels according to claim 11, wherein: and a pressure sensor and a shear sensor are superposed in adjacent measuring areas.
13. The system for monitoring abnormal operation of a train wheel according to claim 11, wherein: the pressure sensor is arranged on the top surface of the rail bottom of the steel rail at the sleeper, and the shear force sensor is arranged on the rail web of the steel rail.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210708800.3A CN114789743B (en) | 2022-06-22 | 2022-06-22 | Method and system for monitoring abnormal running of train wheels |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210708800.3A CN114789743B (en) | 2022-06-22 | 2022-06-22 | Method and system for monitoring abnormal running of train wheels |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114789743A CN114789743A (en) | 2022-07-26 |
| CN114789743B true CN114789743B (en) | 2022-09-16 |
Family
ID=82463139
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210708800.3A Active CN114789743B (en) | 2022-06-22 | 2022-06-22 | Method and system for monitoring abnormal running of train wheels |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114789743B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115560693A (en) * | 2022-12-05 | 2023-01-03 | 浙江天铁实业股份有限公司 | Load dynamic monitoring method and system |
| CN116861292A (en) * | 2023-07-10 | 2023-10-10 | 哈尔滨工业大学 | Real-time identification method for road monitoring data loaded dynamic response |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008028697A2 (en) * | 2006-09-06 | 2008-03-13 | Continental Automotive Gmbh | Method and device for monitoring the noise from a sensor |
| CN102914545A (en) * | 2012-11-15 | 2013-02-06 | 潍坊学院 | Gear defect detection method and system based on computer vision |
| CN104228872A (en) * | 2014-09-28 | 2014-12-24 | 江苏润仪仪表有限公司 | Portable track irregularity online monitoring device and method |
| CN105865776A (en) * | 2016-03-23 | 2016-08-17 | 浙江理工大学 | Wind power gear box fault diagnosis method based on EEMD and generalized S transform |
| CN105973618A (en) * | 2016-08-03 | 2016-09-28 | 南京理工大学 | Preliminary assessment method for security domain of wheel service state |
| CN106828543A (en) * | 2017-03-13 | 2017-06-13 | 北京众成探知信息技术有限公司 | A kind of optical fiber distributed type train monitoring system |
| CN109000940A (en) * | 2018-05-04 | 2018-12-14 | 中车青岛四方机车车辆股份有限公司 | A kind of rolling stock exception axis temperature diagnostic method and system |
| CN110222856A (en) * | 2019-06-12 | 2019-09-10 | 中国神华能源股份有限公司 | Processing method, device and the storage medium of railway train wheel tread damage |
| CN111652852A (en) * | 2020-05-08 | 2020-09-11 | 浙江华睿科技有限公司 | Method, device and equipment for detecting surface defects of product |
| CN111814548A (en) * | 2020-06-03 | 2020-10-23 | 中铁第四勘察设计院集团有限公司 | Abnormal behavior detection method and device |
| CN112508883A (en) * | 2020-11-24 | 2021-03-16 | 南京航空航天大学 | Self-adaptive defect identification method for train wheel tread taper hole detection |
| CN113283003A (en) * | 2020-11-13 | 2021-08-20 | 西南交通大学 | High-speed train axle temperature anomaly detection method based on space-time fusion decision |
| CN114166943A (en) * | 2021-12-03 | 2022-03-11 | 四川西南交大铁路发展股份有限公司 | Active rail damage monitoring method and terminal based on nonlinear ultrasonic waves |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9050984B2 (en) * | 2012-04-20 | 2015-06-09 | International Business Machines Corporation | Anomalous railway component detection |
| WO2018050807A1 (en) * | 2016-09-19 | 2018-03-22 | Siemens Aktiengesellschaft | System, prediction unit, and method for predicting a failure of at least one unit for monitoring and/or controlling transportation traffic |
| CN111855055A (en) * | 2020-06-09 | 2020-10-30 | 华东交通大学 | Method for detecting wheel rail force based on rail bottom displacement of steel rail |
| CN112284721A (en) * | 2020-10-16 | 2021-01-29 | 广东石油化工学院 | Double fault analysis method and system for friction and rotor imbalance of large unit |
| CN114580165A (en) * | 2022-02-28 | 2022-06-03 | 国网上海市电力公司 | Transformer substation switch cabinet partial discharge state evaluation method based on high-dimensional index |
-
2022
- 2022-06-22 CN CN202210708800.3A patent/CN114789743B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008028697A2 (en) * | 2006-09-06 | 2008-03-13 | Continental Automotive Gmbh | Method and device for monitoring the noise from a sensor |
| CN102914545A (en) * | 2012-11-15 | 2013-02-06 | 潍坊学院 | Gear defect detection method and system based on computer vision |
| CN104228872A (en) * | 2014-09-28 | 2014-12-24 | 江苏润仪仪表有限公司 | Portable track irregularity online monitoring device and method |
| CN105865776A (en) * | 2016-03-23 | 2016-08-17 | 浙江理工大学 | Wind power gear box fault diagnosis method based on EEMD and generalized S transform |
| CN105973618A (en) * | 2016-08-03 | 2016-09-28 | 南京理工大学 | Preliminary assessment method for security domain of wheel service state |
| CN106828543A (en) * | 2017-03-13 | 2017-06-13 | 北京众成探知信息技术有限公司 | A kind of optical fiber distributed type train monitoring system |
| CN109000940A (en) * | 2018-05-04 | 2018-12-14 | 中车青岛四方机车车辆股份有限公司 | A kind of rolling stock exception axis temperature diagnostic method and system |
| CN110222856A (en) * | 2019-06-12 | 2019-09-10 | 中国神华能源股份有限公司 | Processing method, device and the storage medium of railway train wheel tread damage |
| CN111652852A (en) * | 2020-05-08 | 2020-09-11 | 浙江华睿科技有限公司 | Method, device and equipment for detecting surface defects of product |
| CN111814548A (en) * | 2020-06-03 | 2020-10-23 | 中铁第四勘察设计院集团有限公司 | Abnormal behavior detection method and device |
| CN113283003A (en) * | 2020-11-13 | 2021-08-20 | 西南交通大学 | High-speed train axle temperature anomaly detection method based on space-time fusion decision |
| CN112508883A (en) * | 2020-11-24 | 2021-03-16 | 南京航空航天大学 | Self-adaptive defect identification method for train wheel tread taper hole detection |
| CN114166943A (en) * | 2021-12-03 | 2022-03-11 | 四川西南交大铁路发展股份有限公司 | Active rail damage monitoring method and terminal based on nonlinear ultrasonic waves |
Non-Patent Citations (2)
| Title |
|---|
| 基于振动数据分析的轴承典型故障预测研究;王银刚;《中国优秀硕士学位论文全文数据库（工程科技Ⅱ辑）》;20210115(第1期);全文 * |
| 基于运动模糊红外图像下的铁路货车轮对踏面检测;林颖;《中国优秀硕士学位论文全文数据库(工程科技Ⅱ辑)》;20220215(第2期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114789743A (en) | 2022-07-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114789743B (en) | Method and system for monitoring abnormal running of train wheels | |
| Singh et al. | Rolling element bearing fault diagnosis based on over-complete rational dilation wavelet transform and auto-correlation of analytic energy operator | |
| Amarnath et al. | Exploiting sound signals for fault diagnosis of bearings using decision tree | |
| He et al. | Bearing fault detection based on optimal wavelet filter and sparse code shrinkage | |
| CN106018557B (en) | A kind of raceway surface recess detection method based on wavelet analysis | |
| CN106274983B (en) | A kind of Mechanism Diagnosis method for identifying track traffic wheel On Wheel Rim Fracture | |
| CN109883703B (en) | Fan bearing health monitoring and diagnosing method based on vibration signal coherent cepstrum analysis | |
| EP3384253A1 (en) | Distributed fibre optic sensing for monitoring rail networks | |
| Sheng et al. | Applications in bearing fault diagnosis of an improved Kurtogram algorithm based on flexible frequency slice wavelet transform filter bank | |
| JP6365526B2 (en) | Bearing deterioration detection method and bearing deterioration detection device for small diameter roll | |
| CN102175768A (en) | Method and device for detecting defects and failures of high-speed rail based on vibration signals | |
| CN105865788A (en) | Array acoustic detection method for train bearing defect online monitoring | |
| Shao et al. | Characteristic recognition of chatter mark vibration in a rolling mill based on the non-dimensional parameters of the vibration signal | |
| Chen et al. | Compound fault identification of rolling element bearing based on adaptive resonant frequency band extraction | |
| US20180283992A1 (en) | Wheel condition monitoring | |
| Lin et al. | Instantaneous frequency estimation for wheelset bearings weak fault signals using second-order synchrosqueezing S-transform with optimally weighted sliding window | |
| CN106672015A (en) | Method, device and system for monitoring faults of wheels of motor train unit | |
| Yi et al. | A promising new tool for fault diagnosis of railway wheelset bearings: SSO-based Kurtogram | |
| CN108595374A (en) | High speed railway track geometry minor change recognition methods and device | |
| CN103175897A (en) | High-speed turnout damage recognition method based on vibration signal endpoint detection | |
| CN107064298A (en) | The laser detecting method of blower fan blade cracks in a kind of operation | |
| Meng et al. | Sugarcane node recognition technology based on wavelet analysis | |
| CN105521997A (en) | Method for diagnosing faults of rolling mill roller system on basis of vibration signals | |
| Fang et al. | Reciprocating compressors intelligent fault diagnosis under multiple operating conditions based on adaptive variable scale morphological filter | |
| CN108918173A (en) | A kind of method and system detecting pantograph or cable failure |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |